日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

群制御arXiv:1812.11135

マルチロボットシステムのためのオンライン分散リcedingホライズン軌道最適化

Online Decentralized Receding Horizon Trajectory Optimization for Multi-Robot systems

シェア:XThreadsFacebookLINEはてブBluesky

各ロボットが局所地図と通信で他ロボットの状態を共有し、安全領域を設定して衝突回避軌道をオンラインで最適化する分散型アルゴリズムを提案し、ROS/Gazeboで航空機と車輪ロボットのシミュレーション検証を行った。

著者: Govind Aadithya R, Shravan Krishnan, Vijay Arvindh, Sivanathan K

分類: cs.RO, cs.MA

原文アブストラクト

A novel decentralised trajectory generation algorithm for Multi Agent systems is presented. Multi-robot systems have the capacity to transform lives in a variety of fields. But, trajectory generation for multi-robot systems is still in its nascent stage and limited to heavily controlled environments. To overcome that, an online trajectory optimization algorithm that generates collision-free trajectories for robots, when given initial state and desired end pose, is proposed. It utilizes a simple method for obstacle detection, local shape based maps for obstacles and communication of robots' current states. Using the local maps, safe regions are formulated. Based upon the communicated data, trajectories are predicted for other robots and incorporated for collision-avoidance by resizing the regions of free space that the robot can be in without colliding. A trajectory is then optimized constraining the robot to remain within the safe region with the trajectories represented by piecewise polynomials parameterized by time. The algorithm is implemented using a receding horizon principle. The proposed algorithm is extensively tested in simulations on Gazebo using ROS with fourth order differentially flat aerial robots and non-holonomic second order wheeled robots in structured and unstructured environments.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI